© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 39951
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Zalety
    -1.03
     considerada
    -0.92
     показатели
    -0.88
     of
    -0.88
    r
    -0.86
    了一遍
    -0.85
     заказать
    -0.85
     الت
    -0.85
    Specyfikacja
    -0.83
    ISCH
    -0.81
    POSITIVE LOGITS
    ॠ
    1.14
    chanted
    1.06
    limat
    1.04
    他才
    1.04
     Verteilung
    1.01
    힛
    1.00
     пройдет
    1.00
    )।
    1.00
     filtros
    0.99
    >());
    0.99
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.